© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 14252
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing something or someone in or on board

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to bringing or transferring something or someone

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Doctrine
    -0.62
     motives
    -0.60
    BILITY
    -0.59
     [&
    -0.59
    piring
    -0.59
     motive
    -0.58
     fingerprint
    -0.58
     ($)
    -0.57
    =]
    -0.57
    ĪĴ
    -0.56
    POSITIVE LOGITS
    kefeller
    0.83
    uba
    0.78
    ashtra
    0.76
    rir
    0.76
     cheaply
    0.68
    atel
    0.67
    amate
    0.67
    ascus
    0.67
    unal
    0.66
    ecast
    0.65
    Activations Density 0.111%

    No Known Activations